Expense_Tracker_MCP
An AI-powered expense management server that enables adding, searching, and analyzing expenses using natural language through the Model Context Protocol.
README
💰 Expense Tracker MCP
🤖 AI-Powered Expense Management using Model Context Protocol
<p align="center"> </p> <p align="center"> <img src="https://img.shields.io/badge/Python-3.13-blue?style=for-the-badge&logo=python"/> <img src="https://img.shields.io/badge/FastMCP-3.4.4-purple?style=for-the-badge"/> <img src="https://img.shields.io/badge/MongoDB-Database-green?style=for-the-badge&logo=mongodb"/> <img src="https://img.shields.io/badge/FastAPI-Backend-009688?style=for-the-badge&logo=fastapi"/> </p>
📌 Overview
Expense Tracker MCP is an AI-powered financial management system built usingModel Context Protocol (MCP ).
The system allows Large Language Models to interact with expense data throughMCP tools, enabling users to:
-
Add expenses
-
Search expenses
-
Analyze spending patterns
-
Generate financial insights
-
Communicate with expense data using natural language
🧠 MCP Architecture
flowchart TB
USER["👤 User"]
CLIENT["🔌 MCP Client"]
SERVER["⚡ FastMCP Server"]
TOOLS["🛠 MCP Tools"]
FASTAPI["🚀 FastAPI Application"]
MONGO["🍃 MongoDB Database"]
USER --> CLIENT
CLIENT --> SERVER
SERVER --> TOOLS
TOOLS --> FASTAPI
FASTAPI --> MONGO
🚀 Key Features
💸 Expense Management✅ Create expenses✅ Update expenses✅ Delete expenses✅ Retrieve expense records✅ Store financial history
🔌 Model Context Protocol
This project implements MCP architecture:
User|MCP Client|FastMCP Server|Expense Tools|MongoDB
🛠️ Technology Stack
###🐍 Core Development
<p align="center"> <img src="https://skillicons.dev/icons?i=python"/> </p> Python >= 3.13 Setuptools Wheel
⚡ MCP Framework
<img src="https://img.shields.io/badge/FastMCP-3.4.4-purple?style=flat-square"> MCP Server implementation Tool registration LLM communication layer
🚀 Backend
<p align="center"> <img src="https://skillicons.dev/icons?i=fastapi"/> </p> FastAPI Uvicorn REST APIs
🍃 Database
<p align="center"> <img src="https://skillicons.dev/icons?i=mongodb"/> </p> MongoDB PyMongo Motor Async Driver
📦 Validation & Configuration
Pydantic v2Pydantic SettingsEnvironment Variablespython-dotenv
📂 Project Structure
Expense_Tracker/
│
├── app/
│ └── db/
│ ├── database.py # MongoDB connection configurations & client initialization
│ └── application.py # Core FastAPI application routing and logic
│
├── mcp/
│ ├── mcp_client.py # MCP Client implementation for context bridging
│ └── mcp_server.py # FastMCP Server registering the operational tools
│
├── .env # Local environment variable configuration
├── .gitignore # Specified version control exclusions (e.g., venv, __pycache__ )
├── .python-version # Explicit python version pinning
├── pyproject.toml # Project metadata, dependencies, and editable tool configurations
└── README.md # System documentation## ⚙️ Installation
Clone repository:
git clone https://github.com/YOUR_USERNAME/Expense-Tracker-MCP.git
cd Expense-Tracker-MCP
Install dependencies:
pip install -e .
🔐 Environment Configuration
Create .env
MONGODB_URI=your_mongodb_connection_string
DATABASE_NAME=expense_tracker
▶️ Running Application
Start MCP Server
-expense-server
or
python mcp_server.py
🌐 Remote MCP Server
This project also provides a remote MCP server that users can connect to:https://expense-tracker-01.fastmcp.app/mcp
API Documentation:
http://localhost:8000/docs
🔮 Future Improvements
-Expense prediction using ML-Budget recommendation engine-Voice-based expense entry-Multi-user authentication-React dashboard-Cloud deployment-Mobile application
👨💻 Developer
Sarim Abbas
AI Engineer | Backend Developer | Agentic AI Developer
<p align="center"> <img src="https://skillicons.dev/icons?i=python,fastapi,mongodb,docker,aws"/> </p>
⭐ Star this repository if you find it useful!
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。